A Study To Develop A Turkish Sentiment Lexicon On Brand Image

Yıl 2021, , 415 - 433, 30.12.2021

Emel Özdemir Akcan

https://doi.org/10.26650/acin.908724

Öz

In recent years, sentiment analysis has emerged as one of the most useful methods for businesses in order to determine the comments and thoughts of users, to reveal their opinion and emotions about brands. From a methodological perspective, the fact that general lexicons do not adequately represent brand terms in the domain of brand image, that there is no sentiment lexicon in Turkish in the context of the brand, and the fact that there are very few studies that reveal the brand image with sentiment analysis reveal the deficiency in this domain. In this context, the purpose of this research is to create a Turkish lexicon that is necessary for sentiment analysis in order to determine the perception of the image of the brand in users’ minds. In order to achieve this aim, 113 Turkish theses in the higher education institution (YÖK) related to brand image were scanned, and the most frequently mentioned words in them were tried to be determined with the sentiment analysis method by R programming language. The total number of words obtained in the data set of the field of brand image was observed as 1,738,596. Among these words, the most frequently used words in the field of brand image were obtained as 31,671. The brand image lexicon was created with 9535 words which express sentiment in the domain of brand image among the 31,671 words used most frequently.

Anahtar Kelimeler

Brand Image, Social Media, Sentiment Analysis, R, Sentiment Lexicon

Marka İmajı Üzerine Türkçe Duygu Sözlüğü Geliştirme Çalışması

Öz

Son yıllarda kullanıcıların yorum ve düşüncelerini belirleyebilmek, markalar hakkındaki düşünce ve duygularını ortaya çıkarabilmek amacı ile duygu analizi, işletmeler açısından en kullanışlı yöntemlerden birisi olarak karşımıza çıkmaktadır. Yöntem bilimsel bakış açısıyla genel sözlüklerin marka imajı alanına ait marka terimlerini yeteri kadar temsil edememesi, Türkçe olarak marka bağlamında duygu sözlüğünün yer almaması ve marka imajını duygu analizi ile ortaya koyan çalışmaların son derece az olması, bu alandaki eksikliği ortaya koymaktadır. Bu kapsamda bu araştırmanın amacı markaların kullanıcıların zihnindeki imaj algısını belirleyebilmek adına duygu analizi için gerekli olan bir Türkçe sözlük oluşturmaktır. Bu amacı gerçekleştirmek için, marka imajı ile ilgili yükseköğretim kurumundaki (YÖK) 113 Türkçe tez taranarak, içerisinde en çok geçen kelimeler R programlama dili kullanılarak, duygu analizi yöntemi ile tespit edilmeye çalışılmıştır. Marka imajı alanına ait veri setinde toplamda elde edilen kelime sayısı 1.738.596 adet olarak gözlemlenmiştir. Bu kelimeler içerisinde marka imajı alanında en sık kullanılanlar ise 31.671 adet kelime olarak elde edilmiştir. En sık kullanılan 31.671 kelimenin içerisinde marka imajı alanında duygu ifade eden 9535 adet kelime ile marka imajı sözlüğünü oluşturulmuştur.

Anahtar Kelimeler

Marka imajı, Sosyal Medya, Duygu Analizi, R, Duygu Sözlüğü

Kaynakça

• Aaker, D.A.& Biel, A.L. (1993). Brand Equity Ve Advertising: Advertising’s Roles İn Building Strong Brands. Lawrence Erlbaum Associates, New Jersey.
• Abdul-Mageed, M., Diab, M.T. & Korayem, M. (2011). Subjectivity And Sentiment Analysis Of Modern Standard Arabic, The 49th Annual Meeting Of The Association For Computational Linguistics (Short Papers), 587–591.
• Abdul-Mageed, M., Kübler, S. & Diab, M. (2012). SAMAR: A System For Subjectivity And Sentiment Analysis Of Arabic Social Media, Proceedings Of The 3rd Workshop İncomputational Approaches To Subjectivity And Sentiment Analysis, 28(1), 20-37.
• Akbaş, E., (2012). Aspect Based Opinion Mining On Turkish Tweets, Yüksek Lisans Tezi, Bilkent Üniversitesi, Mühendislik ve Fen Bilimleri Enstitüsü, Ankara. Akhtar.
• Akgül, E.S., Ertano, C. & Diri, B. (2016). Twitter Verileri İle Duygu Analizi. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 22(2), 106-110.
• Al-Ayyoub, M., Essa, B.S. & Alsmadi, I. (2015). Lexicon-Based Sentiment Analysis Of Arabic Tweets, Int. J. Social Network Mining, X (Y), XXXX.
• Aue, A. & Gamon, M. (2005). Customizing Sentiment Classifiers To New Domains: A Case Study, In Proceedings Of The International Conference On Recent Advances İn Natural Language Processing, Borovets, Bulgaria.
• Aytekin, Ç., (2013). An Opinion Mining Task İn Turkish Language A Model For Assigning Opinions İn Turkish Blogs To The Polarities, Journalism And Mass Communication, 3, 179-198.
• Baccianella, S., Esuli, A., & Sebastiani, F. (2010). Sentiwordnet 3,0: An Enhanced Lexical Resource For Sentiment Analysis And Opinion Mining, Proceedings Of The 7th International Conference On Language Resources And Evaluation, 10, 2200-2204.
• Balahur, A., Hermida, J.M. & Montoyo, A., (2012). Detecting Implicit Expressions Of Emotion İn Text: A Comparative Analysis, Decision Support Systems, 53, 742-753.
• Bartlett, J. ve Albright, R. (2008). Coming To A Theater Near You! Sentiment Classification Techniques Using SAS Text Miner, In SAS Global Forum, San Antonio, TX.
• Başfırıncı, Ç. (2016). Marka İmajının Sosyal Ağ Analizi ile İncelenmesi: Turkcell ve Vodafone Markalarına Yönelik Bir Araştırma, İstanbul Gelişim Üniversitesi Sosyal Bilimler Dergisi 3(2), 25-50. doi: 10.17336/igusbd.30297
• Bilgin, O., Çetinoğlu, Ö. & Oflazer, K. (2004). Building A Wordnet For Turkish, Romanian Journal Of Information Science And Technology, 7(1-2), 163-172.
• Boiy, E., Hens, P., Deschacht, K. & Moens, M.F., (2007). Automatic Sentiment Analysis Of On-Line Text, In Proceedings Of The 11th International Conference On Electronic Publishing, 349–360, Vienna.
• Boldrini, E., Balahur A., Martı´Nez-Barco, P. & Montoyo A. (2012). Using Emotiblog To Annotate And Analyse Subjectivity İn The New Textual Genres, Data Mining Knowlage Discovery, 25, 603–34.
• Canan, S. (2013). Bir Halkla İlişkiler Aracı Olarak Sosyal Medya Kullanımı: Üç Alana Yönelik Bir İnceleme.Yüksek Lisans Tezi, İstanbul Üniversitesi Sosyal Bilimler Enstitüsü Halkla İlişkiler ve Tanıtım Anabilim, İstanbul.
• Cebeci, H.İ. (2020). Mühendislikte Yapay Zekâ ve Uygulamaları 3: Sosyal Medya Verileri ile Duygu Analizi (191-211). Sakarya Üniversitesi Mühendislik Fakültesi, Sakarya: Sakarya Üniversitesi.
• Chaovalit, P. & Zhou, L. (2005). Movie Review Mining: A Comparison Between Supervised And Unsupervised Classification Approaches, In Proceedings Of The 38th Hawaii International Conference On System Sciences, Hawaii.
• Chen, M., Mao S., Zhang Y., & Leung V.C.M. (2014). Big Data Related Technologies, Challenges And Future Prospect. Springer Briefs İn Computer Science, 2-3.,Newyork, Springer.
• Chia-Hung, H. (2008). The Effect Of Brand İmage On Public Relations Perceptions And Customer Loyalty. International Journal Of Management, 25(2): 237- 246.
• Christodoulides, G. & De Chernatony, L. (2010). Consumer-Based Brand Equity Conceptualization And Measurement: A Literature Review. International Journal Of Market Research, 52 (1), 43-66.
• Clow, K., Baack, D. (2016). Bütünleşik Reklam, Tutundurma Ve Pazarlama İletişimi. Ankara: Nobel Akademik Yayıncılık. Copeland, M.T. (1923). Relation Of Consumers’ Buying Habits To Marketing Methods. Harvard Business Review, 1(3), 282-289.
• Davcik, N.S. & Rundquist, J. (2012). An Exploratory Study Of Brand Success: Evidence From The Food İndustry. Journal Of International Food And Agribusiness Marketing, 24 (1), 1-119.
• Dehkharghani, R., Saygin, Y., Yanikoglu, B., & Oflazer, K. (2015). Sentiturknet: A Turkis Polarity Lexicon For Sentiment Analysis, Language Resources And Evaluation, 50(3), 667-685.
• Ding, X., Liu, B., ve Yu, P. S. (2008). A Holistic Lexicon-Based Approach To Opinion Mining, Proceedings Of The 2008 International Conference On Web Search And Data Mining, 231-240.
• Esuli A. & Sebastiani F. (2006). Sentiwordnet: A Publicly Available Lexical Resource For Opinion Mining, In Proceedings of 5th International Conference on Language Resources and Evaluation (LREC), 417–422.
• Fellbaum, C. (1998). Wordnet: An Electronic Lexical Database, MIT Press.
• Fernández-Gavilanes, M., Álvarez-López, T., Juncal-Martínez, J., Costa-Montenegro, E. & González-Castaño, F.J. (2016). Unsupervised Method For Sentiment Analysis İn Online Texts, Expert Syst. Appl. 58, 57–75. Gardner, B.B. & Levy, S. J. (1955). The Product And The Brand. Harvard Business Review 33-39.
• Hatzivassiloglou, V. ve Mckeown, K. (1997). Predicting The Semantic Orientation Of Adjectives, In Proceedings Of 35th Meeting Of The Association For Computational Linguistics, 174–181.
• Hu, M., & Liu, B. (2004). Mining And Summarizing Customer Reviews, İn Proceedings Of The Tenth ACM SIGKDD International Conference On Knowledge Discovery And Data Mining, New York, 168-177.
• İdeasoft, (2021). https://www.İdeasoft.Com.Tr/Marka-Konumlandirma-Nedir/ (Erişim 25.07.2021) İş verileri platformu,(2020) http/www.statista.com/topics/1164/social-networks/(Erişim, 20.01.2020).
• Jones, R. (2010). Corporate Branding: The Role Of Vision İn İmplementing The Corporate Brand, Innovative Marketing, 6 (1),44-57.
• Kang, D.& Park, Y., (2014). Review-Based Measurement Of Customer Satisfaction İn Mobile Service: Sentiment Analysis And VIKOR Approach, Expert Systems With Applications, 41, 1041-1050.
• Kang, H., Yoo, S.J. & Han, D. (2012). Senti-Lexicon And Improved Naïve Bayes Algorithms For Sentiment Analysis Of Restaurant Reviews, Expert Systems With Applications, 39, 6000-6010.
• Karoui, J., Zitoune, F. B. & Moriceau, V. (2019). Automatic Detection Of Irony, John Wiley & Sons.
• Kaufmann, JM. Jmaxalign, (2012). A Maximum Entropy Parallel Sentence Alignment Tool, In: Proceedings Of COLING’12: Demonstration Papers, Mumbai, 277–88.
• Kaya, M., Fidan, G.& Toroslu, I.H. (2012). Sentiment Analysis Of Turkish Political News, In Proceedings Of WI-IAT’12 IEEE/WIC/ACM International Joint Conferences On Web İntelligent Agent Technology, Macau, Çin, 174-180.
• Kennedy, A. & Inkpen, D. (2006). Sentiment Classification Of Movie And Product Reviews Using Contextual Valence Shifters, Computational Intelligence, 22(2):110–125.
• Khan, F.H., Qamar, U. & Bashir, S. (2016). Esap: A Decision Support Framework For Enhanced Sentiment Analysis And Polarity Classification, Information Sciences, 367(368), 862–873. doi: 10.1016/j.ins.2016.07.028
• Kouloumpis, E, Wilson, T.& Moore, J. (2011). Twitter Sentiment Analysis: The Good The Bad And The Omg!, Proceedings Of The Fifth International AAAI Conference On Weblogs And Social Media (ICWSM), 538-541 Liu, B. (2020). Sentiment Analysis: Mining Opinions, Sentiments, And Emotions, Cambridge University Press.
• Medhat, W., Hassan, A. & Korashy, H., (2014). Sentiment Analysis Algorithms And Applications: A Survey, Ain Shams Engineering Journal, 5,1093- 1113. doi: 10.1016/j.asej.2014.04.011
• Meenaghan, T., (1995). The Role Of Advertising İn Brand Image Development. Journal Of Product Ve Brand Management., 4(4): 23-34.
• Mohammad, S.M. & Turney, P.D. (2013). Crowdsourcing A Word-Emotion Association Lexicon ( NRC), Computational Intelligence, 29(3) ,436-465.
• Nielsen, F. A. (2011). A New ANEW: Evaluation Of A Word List For Sentiment Analysis İn Microblogs, In Proceedings of the ESWC2011 Workshop on ‘Making Sense of Microposts’: Big things come in small packages (pp. 93-98). CEUR Workshop Proceedings No. 718 http://research.hypios.com/ msm2011/ Workshop On Making Sense Of Microposts, 93-98.
• Nigam, K. & Hurst, M. (2004). Towards A Robust Metric Of Opinion, AAAI Spring Symposium On Exploring Attitude And Affect İn Text, 598–603.
• Oza, K.S. & Naik, P.G. (2016). Prediction Of Online Lectures Popularity: A Text Mining Approach” Procedia Computer Science, 92, 468–474. doi: 10.1016/j.procs.2016.07.369
• Öztürk, N. & Ayvaz, S. (2018). Sentiment Analysis On Twitter: A Text Mining Approach To The Syrian Refugee Crisis, Telematics And Informatics, 35(1), 136-147. doi: 10.1016/j.tele.2017.10.006
• Park, C.S. & Srinivasan, V. (1994). A Survey-Based Method For Measuring And Understanding Brand Equity And Its Extendibility. Journal Of Marketing Research, 31 (2), 271-288.
• Park, S., Lee, W. & Moon, I.C. (2015). Efficient Extraction Of Domain Specific Sentiment Lexicon With Active Learning, Pattern Recognition Letters, 56, 38-44. doi: 10.1016/j.patrec.2015.01.004
• Paswan, A., Guzman, F., & Blankson, C. (2012). Business To Busniess Governance Structure Andmarketing Strategy. Industrial Marketing Management, 41 (6), 908-918.
• Pradhan, V. M., Vala, J.& Balani, P. (2016). A Survey On Sentiment Analysis Algorithms For Opinion Mining”, International Journal Of Computer Applications, 133(9), 7-11.
• Robaldo L. & Di Caro L. (2012). Opinionmining-ML, Comput Stand Interfaces, 35(5),454-469. Sevindi, B.İ. (2013). Türkçe Metinlerde Denetimli ve Sözlük Tabanlı Duygu Analizi Yaklaşımlarının Karşılaştırılması, Yüksek Lisans Tezi, Gazi Üniversitesi, Fen Bilimleri Enstitüsü, Ankara.
• Smith, R.J. (1915). Market Distribution Discussion: J. Russell Smith. American Economic Review, 5(1), 157-158.
• Srinivasan, V., Park, C. & Chang, D. (2005). An Approach To The Measurement, Analysis And Prediction Of Brand Equity And Its Sources. Management Science, 51 (9). 1433-1448.
• Steinberger J., Ebrahim M., Ehrmann M., Hurriyetoglu A., Kabadjov M., Lenkova P., Steinberger R., Tanev H., Va´ Zquez S. & Zavarella V. (2012). Creating Sentiment Dictionaries Via Triangulation, Decision Support System, 53, 689–94.
• Stone, P.J., Dunphy, D.C., Smith, M.S. & Ogilvie, D. M. (1966). The General Inquirer: A Computer Approach To Content Analysis, MIT Press, Cambridge..
• Şimşek, M.U. & Özdemir, S. (2012). Analysis Of The Relation Between Turkish Twitter Messages And Stock Market Index, In Procedings Of AICT ‘12, 6th Conference On Application Of Information And Communication Technologies, Tiflis, Gürcistan, 1-4.
• Taboada, M., Brooke, J., Tofiloski, M., Voll, K. & Stede, M., (2011). Lexicon-Based Methods For Sentiment Analysis, Computational Linguistics, 37(2), 267-307.
• Thelwall, M., Buckley, K., Paltoglou, G., Cai, D.& Kappas, A. (2010). Sentiment Strength Detection İn Short İnformal Text, J. Am. Soc. Information Science Technologies, 61 (12), 2544-2558.
• Tong, R. M. (2001). An Operational System For Detecting And Tracking Opinions İn On-Line Discussions, In Working Notes Of The ACM SIGIR Workshop Operational Text Classification, , New York, NY. 1–6.
• Türkmenoğlu, C. (2015). Türkçe Metinlerde Duygu Analizi. İstanbul Teknik Üniversitesi, Bilgisayar Mühendisliği Abd, Yüksek Lisans Tezi, İstanbul.
• Vural, G.A, Cambazoğlu, B.B., Senkul, P. & Tokgoz, Ö. Z. (2012). A Framework for Sentiment Analysis In Turkish: Application To Polarity Detection Of Movie Reviews In Turkish, Computer And Information Science III., 437-445.
• Wiebe J., Wilson T., & Cardie C. (2005).Annotating Expressions Of Opinions And Emotions İn Language, Language Resources And Evaluation, 33(2-3), 164-210.
• Xie, R. & Li, C. (2012). Lexicon Construction: A Topic Model Approach, In Systems And Informatics (ICSAI), International Conference, 2299-2303.
• Yi, J., Nasukawa, T., Bunescu, R., & Nıblack, W. (2003). Sentimentanalyzer: Extracting Sentiments About A Given Topic Using Natural Language Processing Techniques, In: Proceedings Of Third IEEE International Conference on Data Mining, 427-434.